© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28990
    Prev
    Next
    INDEX
    Explanations

    specific references to events or ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ©ãĤ¤ãĥĪ
    -0.07
    jing
    -0.07
    ambi
    -0.06
    isel
    -0.06
    677
    -0.06
    ington
    -0.06
    152
    -0.06
    iva
    -0.06
    egra
    -0.06
    enge
    -0.06
    POSITIVE LOGITS
    utan
    0.07
    FormattedMessage
    0.06
    otron
    0.06
    letic
    0.06
     Dynamics
    0.06
    âĹĭ
    0.06
    umo
    0.06
    accion
    0.05
    `.`
    0.05
     Watkins
    0.05
    Activations Density 0.078%

    No Known Activations